INDEX

Explanations

verbs indicating possession or occurrence in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Follows "has," "have," or "had."

np_acts-logits-general · gemini-2.0-flash

has/have been

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Erreferentziak

-0.69

enumii

-0.66

tagHelperRunner

-0.65

WebServlet

-0.64

ibatis

-0.62

WriteTagHelper

-0.60

JsonFormat

-0.59

+#+#

-0.58

 CanadaChoose

-0.58

ThemeOverlay

-0.58

POSITIVE LOGITS

 historically

0.91

 traditionally

0.85

 always

0.84

histor

0.76

 often

0.75

 consistently

0.75

 tended

0.72

 repeatedly

0.70

 struggled

0.70

 generally

0.68

Activations Density 0.226%

verbs indicating possession or occurrence in various contexts

Follows "has," "have," or "had."

has/have been

No Comments

No Known Activations